I built a 17-agent AI swarm on my phone — here's how

Description and use

A 17‑agent swarm named Nexus runs locally on Android using TensorFlow Lite for efficient distance calculations and shared memory for communication.

Run a complex multi-agent system locally on an Android device while maintaining performance and privacy.

17‑agent swarm runs locally on Android at ~30 FPS, demonstrating that complex multi‑agent behavior can be achieved offline with modest hardware.

1. Set up Python via Pydroid 3 on Android.
2. Implement agent attributes (position, velocity, energy, perception radius, weights).
3. Code cohesion, separation, alignment functions in NumPy.
4. Create a global list for shared memory and let agents read nearby states directly.
5. Add threading to parallelize agent updates.
6. Profile performance; identify distance calculations as bottleneck.
7. Train a small TensorFlow model to approximate Euclidean distance.
8. Convert model to TensorFlow Lite and integrate into agent loop.
9. Run swarm at ~30 FPS, monitor resource usage.

I built a 17-agent AI swarm on my phone — here's how

TensorFlow Lite is Google’s framework for running TensorFlow models on mobile and embedded devices. It’s optimized for size and speed.

I trained a simple TensorFlow model to approximate the distance between two points.